List your company

Theorem Proving on CombiBench

8Proof LengthClaude 4.6 Opus
4.89225.87146.8567.829Apr 29, 2026

Evaluation results

MethodLinks
Claude 4.6 OpusType=Proprietary LLM2026.048
Gemini 3.1 ProType=Proprietary LLM2026.0415.8
GPT-5.3-CodexType=Proprietary LLM2026.0422.3
Gemini 2.5 ProType=Proprietary LLM2026.0423.8
DreamProverBackbone=Gemini 2.5 Pro, Type=Lemma Learning System2026.0429.6
DreamProverBackbone=Gemini 3.1 Pro, Type=Lemma Learning System2026.0431.3
DreamProverBackbone=GPT-5.3-Codex, Type=Lemma Learning System2026.0437.4
DeepSeek-Prover-V2-7BType=Open-source LLM2026.0441.4
Goedel-Prover-V2-8BType=Open-source LLM2026.0445.3
HilbertBackbone=Gemini 3.1 Pro, Type=Agentic System2026.0463.4
HilbertBackbone=GPT-5.3-Codex, Type=Agentic System2026.0476.5
Goedel-Prover-V2-32BType=Open-source LLM2026.0476.7
HilbertBackbone=Gemini 2.5 Pro, Type=Agentic System2026.0485.7